From 0232a5957283c22785f0a7d0a038045154130f16 Mon Sep 17 00:00:00 2001
From: Will Boyd <will@codersblock.com>
Date: Fri, 28 Feb 2025 14:04:34 -0500
Subject: [PATCH] Better image scraping regex

---
 src/parser.js     | 2 +-
 src/translator.js | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/parser.js b/src/parser.js
index e81c56f..4086501 100644
--- a/src/parser.js
+++ b/src/parser.js
@@ -128,7 +128,7 @@ function collectScrapedImages(allPostData, postTypes) {
 			const postId = postData.childValue('post_id');
 			
 			const postContent = postData.childValue('encoded');
-			const scrapedUrls = [...postContent.matchAll(/<img\s[^>]*?src="(.+?\.(?:gif|jpe?g|png|webp))"[^>]*>/gi)].map((match) => match[1]);
+			const scrapedUrls = [...postContent.matchAll(/<img(?=\s)[^>]+?(?<=\s)src="(.+?)"[^>]*>/gi)].map((match) => match[1]);
 			scrapedUrls.forEach((scrapedUrl) => {
 				let url;
 				if (isAbsoluteUrl(scrapedUrl)) {
diff --git a/src/translator.js b/src/translator.js
index 6c31b81..2d4661a 100644
--- a/src/translator.js
+++ b/src/translator.js
@@ -117,7 +117,7 @@ export function getPostContent(content) {
 	if (shared.config.saveImages === 'scraped' || shared.config.saveImages === 'all') {
 		// writeImageFile() will save all content images to a relative /images
 		// folder so update references in post content to match
-		content = content.replace(/(<img\s[^>]*?src=").*?([^/"]+\.(?:gif|jpe?g|png|webp))("[^>]*>)/gi, '$1images/$2$3');
+		content = content.replace(/(<img(?=\s)[^>]+?(?<=\s)src=")[^"]*?([^/"]+)("[^>]*>)/gi, '$1images/$2$3');
 	}
 
 	// preserve "more" separator, max one per post, optionally with custom label